Data Science Sydney Michael Betancourt
SCALABLE BAYESIAN INFERENCE WITH HAMILTONIAN MONTE CARLO - the promise of big data, inferences are often limited not by sample size but rather by systematic effects. Only by carefully modeling these effects can we take full advantage of the data -- big data must be complemented with big models and the algorithms that can fit them. One such algorithm is Hamiltonian Monte Carlo, which exploits the inherent geometry of the posterior distribution to admit full Bayesian inference that scales to the complex models of practical interest. In this talk I will present a conceptual discussion of the challenges inherent to Bayesian computation and the foundations of why Hamiltonian Monte Carlo in uniquely suited to surmount them.
Видео Data Science Sydney Michael Betancourt канала DataScienceSydney
Видео Data Science Sydney Michael Betancourt канала DataScienceSydney
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![DSS 18-08: ELAINA HYDE: "DATA SCIENCE AND MACHINE LEARNING: A PROCESS WITHIN A PROCESS"](https://i.ytimg.com/vi/oOl7GdQ0VCc/default.jpg)
![John Hawkins on Being Bayesian.](https://i.ytimg.com/vi/5UWzn1dfEYQ/default.jpg)
![DSS July 17: TOM OSBORN "Active Learning"](https://i.ytimg.com/vi/a93omp14vrY/default.jpg)
![David Drai, "The future of AI ops, Data ops, and what lies between"](https://i.ytimg.com/vi/YmoKa2SMHbw/default.jpg)
![DSS Aug 17: NEJLA GHABOOSI "Generative Adversarial Networks"](https://i.ytimg.com/vi/4TzjZbNuv5k/default.jpg)
![DSS 1803: WILLIAM LEE: "MALICIOUS ANDROID APPLICATION DETECTION USING RECURRENT NEURAL NETWORKS"](https://i.ytimg.com/vi/ti9nk7eeVDE/default.jpg)
![Data Science Sydney: YANIR SEROUSSI "Ask why! Finding motives, causes, and purpose in data science"](https://i.ytimg.com/vi/2wqu-drqlpo/default.jpg)
![DSS-2017-11: AHMED FATTAH Is your ML solution viable?](https://i.ytimg.com/vi/MV2ALkU0s_s/default.jpg)
![DR NATALIE TWINE: "Unlocking the secrets in your DNA using Machine learning and Cloud-computing"](https://i.ytimg.com/vi/rKTxyELAluY/default.jpg)
![Data Science Sydney: Daniel Marlay “Model Selection - Theory, Practice and Gotchas”](https://i.ytimg.com/vi/OHH1zSok120/default.jpg)
![Data Science June 17 Eugene Dubossarsky - Freelance Data Science](https://i.ytimg.com/vi/IHnaYyUNLqs/default.jpg)
![Data Science Sydney May 2017: JAMIE HALL on "What's new at Kaggle"](https://i.ytimg.com/vi/D0_aPgIQBrs/default.jpg)
![Jess Wu - Automated Machine Learning](https://i.ytimg.com/vi/AjgLFzhNMMw/default.jpg)
![VARUN NAYYAR: "The Why, How and What of Bayesian Inference"](https://i.ytimg.com/vi/A9r8C2GFR4k/default.jpg)
![DSS 02.18. Sachin Abeywardana "Generative Adversarial Networks"](https://i.ytimg.com/vi/9XerjeD5DC0/default.jpg)
![DSS - May18: Eugene Dubossarsky "Strategic Decision Making"](https://i.ytimg.com/vi/ejjdGoyPVmQ/default.jpg)
![Data Science Sydney: SACHIN ABEYWARDANA "Deep Learning: Easier to Learn than you Think"](https://i.ytimg.com/vi/cyU9LqozRs8/default.jpg)
![DSS-18-08: THOMAS LORIDAN: "MACHINE LEARNING AND TROPICAL CYCLONE RISK MODELING"](https://i.ytimg.com/vi/8J5SnUN1E7g/default.jpg)
![AMIR SALEHIPOUR: "Optimisation and decision making in practice"](https://i.ytimg.com/vi/41_9E62tRGk/default.jpg)
![Data Science Sydney: Jamie Hall “Data Science at Kaggle”](https://i.ytimg.com/vi/54bWcvnUg7k/default.jpg)
![Data Science Sydney 04.17: TIMUR BEHLUL on Hierarchical Modelling](https://i.ytimg.com/vi/LqV3vMYIFG8/default.jpg)